Hacker News: phito

New comment by phito in "AI;DR (AI; Didn't Read)"

phito — Tue, 18 Aug 2026 08:58:48 +0000

It's late and you've already done what most people aren't doing — go rest.

New comment by phito in "The Color of White Light"

phito — Sat, 15 Aug 2026 12:42:56 +0000

Colors only exist in the human brain, they're qualia, interpreted from the mixture of wavelengths our eyes detect.

New comment by phito in "Taste Is All That's Left"

phito — Fri, 07 Aug 2026 07:13:59 +0000

It was always easy to copy software (but yes, even easier now). The hard part is competing with the software that you're copying. Software does not exist in a vacuum. They usually have an already established user base, relationships with partner businesses, more domain knowledge due to having to actually think about the problems they are solving and so on.

You can start by copying but at some point you'll have to differentiate, and you might not be able to do so if you don't understand how your sloppy vibe-copied software works.

New comment by phito in "Agent-Manager: A Tmux TUI for Running Claude Code, Codex and OpenCode"

phito — Thu, 30 Jul 2026 14:06:07 +0000

Same here, I do not see the point of herdr if you're already using tmux. It's very easy to add hooks to your favorite harness to display a notification in tmux when it's done working.

New comment by phito in "Re: Bye Bye Gravatar"

phito — Sat, 25 Jul 2026 05:22:27 +0000

Myeah, the first thing I saw when opening it on mobile is that the top logo is not centered and the menu is not displaying properly ("About" item single on a line with some random left margin).

Not that I care but then I was confused by the two comments here praising the design.

New comment by phito in "Why is there smoke from the boiler room? – Botanical Garden using Home Assistant"

phito — Thu, 09 Jul 2026 12:32:03 +0000

At this point it might be easier to point out articles not written by LLM. Most of them are, I just can't bring myself to read them anymore, it feels like a waste of time. I want to read original thoughts and it's almost impossible to know if this kind of content contains any. I'm tired.

New comment by phito in "EU Parliament greenlights Chat Control 1.0"

phito — Thu, 09 Jul 2026 12:05:10 +0000

Does this apply only to new messages or also to history?

New comment by phito in "Zero-Downtime Deployments with Docker Compose – No Kubernetes Required"

phito — Thu, 25 Jun 2026 11:58:52 +0000

We do this because we need redundancy. Are there non kubernetes alternatives for HA/redundancy that are worth it?

New comment by phito in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

phito — Sat, 13 Jun 2026 04:05:47 +0000

What do you mean, companies are already paying for almost good. Coding is indeed serious work and not even Fable is good enough for serious work.

New comment by phito in "They’re made out of weights"

phito — Thu, 04 Jun 2026 05:02:31 +0000

Also there's a brain, the GPU

New comment by phito in "Throwing AI-generated walls of text into conversations"

phito — Fri, 22 May 2026 11:21:28 +0000

That's a good question... => I didn't think about this, I don't know the answer yet.

That's a great question! => I can tell you understood what I explained and used that understanding to reach the next step of reasoning just like I did.

New comment by phito in "Going full AI engineer, not touching code anymore"

phito — Tue, 19 May 2026 15:34:55 +0000

I agree, just like some people decide that they're OK with eating junk food every day, knowing the long term risk. They are free to take it.

New comment by phito in "Going full AI engineer, not touching code anymore"

phito — Tue, 19 May 2026 14:41:45 +0000

> If I do ask an LLM another question about something small it will offer solutions but doesn’t offer the solution I think makes sense in the architectures I’ve written.

This is my experience as well, and I've been using Claude Code a lot.

Extremely impressive tools, but they're like fast food. They will solve your immediate problems quickly and cheaply, but you're going to have issues on the long term if that's all you use.

New comment by phito in "Multiple commencement speakers booed for AI comments during graduation speeches"

phito — Mon, 18 May 2026 11:02:12 +0000

I use AI a lot for development, but I am not sure why students should "embrace" the new technology made to take the job they are studying for.

New comment by phito in "AI should elevate your thinking, not replace it"

phito — Mon, 27 Apr 2026 07:20:44 +0000

It's true for all automation we do get more comfort. We build systems so that we humans have as little struggle as possible, not realising that struggle is the only reason for existence. By eliminating it, we are erasing ourselves from this world.

New comment by phito in "Over-editing refers to a model modifying code beyond what is necessary"

phito — Thu, 23 Apr 2026 07:39:31 +0000

You're wasting a ton of tokens doing that though. Right now you don't realize it because they're being heavily subsidized, but you will understand the point of have good orchestration and memory files when you will have to pay the real cost of your use.

New comment by phito in "Make Tmux Pretty and Usable"

phito — Mon, 13 Apr 2026 15:03:35 +0000

OP doesn't seem to be on Mac

New comment by phito in "How the AI Bubble Bursts"

phito — Mon, 30 Mar 2026 13:09:34 +0000

I think their current goal is to capture as much market as they can while they still have the best models, their only moat. Look at Anthropic, they are clearly trying to lock their users in their ecosystem by refusing to follow conventions (AGENT.md etc) and restricting their tools exclusively to their own services.

New comment by phito in "Hold on to Your Hardware"

phito — Sat, 28 Mar 2026 06:06:58 +0000

Less RAM usage doesn't equal better performances or faster software. It actually might mean the opposite, if you're not caching things in RAM.

New comment by phito in "Ask HN: How do you deal with people who trust LLMs?"

phito — Thu, 19 Mar 2026 05:32:27 +0000

While some of the ideas in this do resonate with me (or at least they're entertaining), it's unfortunate that's it's so obviously LLM generated. And some parts of it, like the INTJ exceptionalism, reek of LLM sycophancy, which then turned into to some kind of god complex...